Added initial files

app.py

@@ -0,0 +1,8 @@
+import gradio as gr
+from inference import *
+
+def greet(name):
+    return "Hello " + name + "!"
+
+iface = gr.Interface(fn=inference, inputs="audio", outputs="text")
+iface.launch()

gtzan10_lstm_0.7179_l_1.12.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810bee018dd749eeb44e51f54435a96a813ce36721f24126687f061232a9e8bb
+size 19417544

inference.py

@@ -0,0 +1,60 @@
+import math, librosa
+import numpy as np
+
+from tensorflow import keras
+
+SAMPLE_RATE = 22050
+def extract_mfcc_batch(file_path, n_mfcc=13, n_fft=1024, hop_length=512, length_segment=10):
+    """
+    Extract and return an mfcc batch
+    MFCC - Mel Frequency Cepstrum Coefficients
+    """
+    mfcc_batch = []
+    num_samples_per_segment = 220500 #length_segment * SAMPLE_RATE
+    expected_num_mfcc_vectors_per_segment = math.ceil(num_samples_per_segment / hop_length)
+   
+    signal, sr = librosa.load(file_path, sr=SAMPLE_RATE)
+
+    duration = librosa.get_duration(y=signal, sr=sr) #30 seconds
+    num_segments = int(duration/length_segment) #3
+    # process segments, extracting mfccs and storing data
+    for s in range(num_segments+1):
+        start_sample = num_samples_per_segment * s
+        finish_sample = start_sample + num_samples_per_segment
+        try:
+            mfcc = librosa.feature.mfcc(signal[start_sample:finish_sample],
+                                    sr=SAMPLE_RATE,
+                                    n_fft=n_fft,
+                                    n_mfcc=n_mfcc,
+                                    hop_length=hop_length
+                                    )
+            #(13, 431)
+            mfcc = mfcc.T # A transpose
+            # store mfcc for segment if it has the expected length
+            if len(mfcc) == 431:
+                mfcc_batch.append(mfcc.tolist())
+        except:
+            continue
+    return mfcc_batch
+
+def inference(filename, model_path='gtzan10_lstm_0.7179_l_1.12.h5'):
+    model = keras.models.load_model(model_path)
+    mapping = ['blues',
+                'classical',
+                'country',
+                'disco',
+                'hiphop',
+                'jazz',
+                'metal',
+                'pop',
+                'reggae',
+                'rock']
+    mfcc = extract_mfcc_batch(filename)
+    pred = model.predict(mfcc)
+    genre = [mapping[i] for i in np.argmax(pred, axis=1)]
+
+    counter_ = {}
+    for i in genre:
+        counter_[genre.count(i)] = i
+    m = max(counter_)
+    return f"Genre: {counter_[m]}, Confidence: {max(counter_)/pred.shape[0]}"

requirements.txt

@@ -0,0 +1,102 @@
+absl-py==1.0.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+anyio==3.5.0
+appdirs==1.4.4
+asgiref==3.5.0
+astunparse==1.6.3
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+backoff==1.10.0
+bcrypt==3.2.0
+cachetools==5.0.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.12
+click==8.0.4
+colorama==0.4.4
+cryptography==36.0.1
+cycler==0.11.0
+decorator==5.1.1
+fastapi==0.74.0
+ffmpy==0.3.0
+flatbuffers==2.0
+fonttools==4.29.1
+frozenlist==1.3.0
+gast==0.5.3
+google-auth==2.6.0
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+gradio==2.8.1
+grpcio==1.44.0
+h11==0.13.0
+h5py==3.6.0
+idna==3.3
+importlib-metadata==4.11.1
+Jinja2==3.0.3
+joblib==1.1.0
+keras==2.8.0
+Keras-Preprocessing==1.1.2
+kiwisolver==1.3.2
+libclang==13.0.0
+librosa==0.9.1
+linkify-it-py==1.0.3
+llvmlite==0.38.0
+Markdown==3.3.6
+markdown-it-py==2.0.1
+MarkupSafe==2.1.0
+matplotlib==3.5.1
+mdit-py-plugins==0.3.0
+mdurl==0.1.0
+monotonic==1.6
+multidict==6.0.2
+numba==0.55.1
+numpy==1.21.5
+oauthlib==3.2.0
+opt-einsum==3.3.0
+packaging==21.3
+pandas==1.4.1
+paramiko==2.9.2
+Pillow==9.0.1
+pooch==1.6.0
+protobuf==3.19.4
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser==2.21
+pycryptodome==3.14.1
+pydantic==1.9.0
+pydub==0.25.1
+PyNaCl==1.5.0
+pyparsing==3.0.7
+pyspark==3.2.0
+python-dateutil==2.8.2
+python-multipart==0.0.5
+pytz==2021.3
+requests==2.27.1
+requests-oauthlib==1.3.1
+resampy==0.2.2
+rsa==4.8
+scikit-learn==1.0.2
+scipy==1.8.0
+six==1.16.0
+sniffio==1.2.0
+SoundFile==0.10.3.post1
+starlette==0.17.1
+tensorboard==2.8.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.8.0
+tensorflow-io-gcs-filesystem==0.24.0
+termcolor==1.1.0
+tf-estimator-nightly==2.8.0.dev2021122109
+threadpoolctl==3.1.0
+typing_extensions==4.1.1
+uc-micro-py==1.0.1
+urllib3==1.26.8
+uvicorn==0.17.5
+Werkzeug==2.0.3
+wrapt==1.13.3
+yarl==1.7.2
+zipp==3.7.0